HIME API Portal/AI・機械学習

AI・機械学習

18 件のAPI

Audio APIby OpenAI🇺🇸

Whisper (STT) and TTS

RESTbearerspeech-to-texttext-to-speech
Chat APIby DeepSeek🇨🇳

DeepSeek models via OpenAI-compatible API

RESTbearerchatreasoningcodingfunction-calling
Chat Completionsby OpenAI🇺🇸

GPT models — chat, vision, function calling

RESTbearerchatvisionfunction-callingstreaming
Chat Completionsby Groq🇺🇸

Ultra-fast LLM inference — Llama, Mixtral, Gemma

RESTbearerchatfastopen-source-models
Chat Completionsby Perplexity🇺🇸

AI search with real-time web grounding

RESTbearersearchragreal-timecitations
Chat Completionsby Azure OpenAI🇺🇸

GPT models with enterprise security on Azure

RESTapi_keychatenterprisemanagedcontent-filter
Embeddings (via Voyager)by Anthropic🇺🇸

Text embeddings via Voyager models

RESTapi_keyembeddingsemantic-search
Embeddings APIby OpenAI🇺🇸

Text embeddings for search and classification

RESTbearerembeddingsemantic-search
Gemini APIby Google AI🇺🇸

Gemini models — multimodal AI

RESTapi_keychatvisionaudiovideo+1
Image Generation APIby Stability AI🇬🇧

Stable Diffusion 3.5 and SDXL image generation

RESTbearerimage-generationinpaintingupscalingsd3
Images APIby OpenAI🇺🇸

DALL-E image generation and editing

RESTbearerimage-generationediting
Inference APIby Hugging Face🇺🇸

Run 300,000+ open-source models via API

RESTbearerinferenceopen-sourcenlpvision+1
InvokeModelby Amazon Bedrock🇺🇸

Call Claude, Llama, Mistral, and more from a single API

RESTbearerinferencemulti-modelmanagedrag
Messages APIby Anthropic🇺🇸

Claude models via Messages API — text, vision, tool use

RESTapi_keychatvisiontool-usestreaming+1
NLU APIby IBM watsonx🇺🇸

Sentiment, entities, keywords, categories extraction

RESTbearernlusentimententitiesclassification
Predictions APIby Replicate🇺🇸

Run open-source models — SDXL, Llama, Whisper

RESTbearerinferenceimage-genopen-sourceasync
Speech-to-Textby Deepgram🇺🇸

Real-time and pre-recorded transcription — 50+ languages

RESTapi_keysttrealtimebatchdiarization+1
Text to Speech APIby ElevenLabs🇺🇸

Realistic text-to-speech with voice cloning

RESTapi_keyttsvoice-cloningstreaming